Do you want to play a game? Learning to play Tic-Tac-Toe in Hypermedia Environments

TL;DR

This paper presents a system where agents in a hypermedia environment learn to play Tic-Tac-Toe using transfer learning, RDF reasoning, and reinforcement learning, enabling collaborative and web-exploiting strategies.

Contribution

It introduces a novel integration of transfer learning with multi-agent hypermedia systems using RDF and reinforcement learning for game playing.

Findings

Agents successfully learned to play Tic-Tac-Toe.

Transfer learning accelerated individual agent learning.

Agents exploited web data for improved strategies.

Abstract

We demonstrate the integration of Transfer Learning into a hypermedia Multi-Agent System using the Multi-Agent MicroServices (MAMS) architectural style. Agents use RDF knowledge stores to reason over information and apply Reinforcement Learning techniques to learn how to interact with a Tic-Tac-Toe API. Agents form advisor-advisee relationships in order to speed up individual learning and exploit and learn from data on the Web.